Classical Text Punctuation
Auto-segment and punctuate unpunctuated classical Chinese passages.
I. Tool
Operation
子曰：「學而，時習之，不亦說乎。有朋自遠方來不亦樂乎。人不知而，不慍不亦君子乎。
。 after 也 矣 乎 哉 焉 耳 歟 邪 耶 爾
， after 之 者 而 則 於 以 與 且 乃 故 然 雖 若
， before 夫 蓋 凡 故 然則 是以 所以 若夫 且夫 至於
A rule table, not a parser: it marks candidate boundaries for you to accept or reject.
II. Principle
How it works
A rule-based segmenter scans the input for classical function-word markers (之, 者, 也, 乎, 矣, 哉, 焉, 而, 則, 於) and dialogue introducers (曰, 云, 問). It inserts punctuation at high-confidence break points and leaves ambiguous stretches untouched for manual review.
III. Guide
User guide
- 01Paste an unpunctuated passage into the input box.
- 02Click Punctuate. The output preserves original characters and adds 。 , : and 「」 where confidence is high.
- 03Review flagged positions (shown with a dotted underline) to confirm or edit the break.
IV. FAQ
Frequently asked
Q.Is this a neural model?
A.No — it is a transparent rule set. Use it as an assistant, not as ground truth.
Q.Will it work on parallel prose (駢文)?
A.Yes, and it favours four/six-character parallel breaks when detected.
V. Related
Tools in the same matrix
Document & Text Processing
Classical Prose Rhythm Detection
Detect tonal patterns and sentence structure in shi and ci poetry.
Auxiliary Research Utilities
Ancient Text Format Standardisation
Normalise typesetting of classical passages for publication.
Document & Text Processing
Classical Word-for-Word Gloss
Character-by-character English gloss for classical Chinese passages.